recipes-design-first
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill content is purely instructional and serves as a coordination hub for a project's development workflow.
- [COMMAND_EXECUTION]: The skill mentions standard local development commands such as
npm run test:runwithin the context of project verification steps. - [DATA_EXPOSURE]: No access to sensitive files (e.g.,
.ssh,.aws,.env) or hardcoded credentials was found. It references standard project directories likedocs/andsrc/static-api/for documentation and static contracts. - [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass AI safety filters or override system instructions.
- [EXTERNAL_DOWNLOADS]: There are no remote code downloads or network requests triggered by this skill.
Audit Metadata